Self-supervised deep reconstruction of mixed strip-shredded text documents.
Thiago M. PaixãoRodrigo Ferreira BerrielMaria C. S. BoeresAlessandro L. KoerichClaudine BadueAlberto F. De SouzaThiago Oliveira-SantosPublished in: Pattern Recognit. (2020)
Keyphrases
- text documents
- text mining
- text classification
- text categorization
- document clustering
- information extraction
- news articles
- keywords
- document classification
- textual information
- topic models
- wordnet
- named entities
- tf idf
- bag of words
- automatic text categorization
- neural network
- data analysis
- learning algorithm
- real world
- databases
- maximum likelihood
- natural language processing
- web pages
- artificial intelligence
- information retrieval